Filters








20,800 Hits in 5.4 sec

A Self-Attentional Neural Architecture for Code Completion with Multi-Task Learning [article]

Fang Liu, Ge Li, Bolin Wei, Xin Xia, Zhiyi Fu, Zhi Jin
<span title="2020-06-26">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To address these challenges, in this paper, we propose a self-attentional neural architecture for code completion with multi-task learning.  ...  To enable the knowledge sharing between related tasks, we creatively propose a Multi-Task Learning (MTL) framework to learn two related tasks in code completion jointly.  ...  In this paper, we propose a self-attentional neural architecture for code completion with Multi-Task Learning (MTL) [5] to address the aforementioned three limitations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.06983v3">arXiv:1909.06983v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/eashpgo275ht7ks6g2tdwsxyzq">fatcat:eashpgo275ht7ks6g2tdwsxyzq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200701164309/https://arxiv.org/pdf/1909.06983v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3d/c3/3dc30a8c838a5f3cf8bb6e775195063fd3354707.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.06983v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learning Deep Semantic Model for Code Search using CodeSearchNet Corpus [article]

Chen Wu, Ming Yan
<span title="2022-01-27">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Recently, deep neural network for code search has been a hot research topic.  ...  We align cross-lingual embedding for multi-modality learning with large batches and hard example mining, and combine different learned representations for better enhancing the representation learning.  ...  Aligning cross-lingual embedding for multimodality learning and combining different learned representations with novel self-attention pooling method are introduced to better understand the query and code  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.11313v1">arXiv:2201.11313v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/er5p53ejsbenjaywdppdrhtcyu">fatcat:er5p53ejsbenjaywdppdrhtcyu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220129183450/https://arxiv.org/pdf/2201.11313v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d7/9c/d79cdd21703d707396154bcc9ce0e2a8bb6bbd73.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.11313v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Multi-branch Attentive Transformer [article]

Yang Fan, Shufang Xie, Yingce Xia, Lijun Wu, Tao Qin, Xiang-Yang Li, Tie-Yan Liu
<span title="2020-07-26">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
While the multi-branch architecture is one of the key ingredients to the success of computer vision tasks, it has not been well investigated in natural language processing, especially sequence learning  ...  is an independent multi-head attention layer.  ...  We will also combine our discoveries with neural architecture search, i.e., searching for better neural models for sequence learning in the search space with enriched multi-branch structures.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.10270v2">arXiv:2006.10270v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zzvgjukwuvbjrjqcanmapon4vm">fatcat:zzvgjukwuvbjrjqcanmapon4vm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200905020335/https://arxiv.org/pdf/2006.10270v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e3/0e/e30ea103674f5b448cb84c06056c77fb1a0d4f59.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.10270v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Survey on Software Defect Prediction Using Deep Learning

Elena N. Akimova, Alexander Yu. Bersenev, Artem A. Deikov, Konstantin S. Kobylkin, Anton V. Konygin, Ilya P. Mezentsev, Vladimir E. Misilov
<span title="2021-05-24">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ye33srllvnanjouxn4tmrfgjsq" style="color: black;">Mathematics</a> </i> &nbsp;
The problem in this area is to properly identify the defective source code with high accuracy.  ...  Our survey focuses on the deep learning techniques for defect prediction.  ...  For example, optimization of the self-attention mechanism for the transformers will allow one to use them for long sequences, which, in the turn, will lead to a more complete consideration of the code  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/math9111180">doi:10.3390/math9111180</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rqpsievq7rcplc7dp3qojyk6le">fatcat:rqpsievq7rcplc7dp3qojyk6le</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210528114000/https://res.mdpi.com/d_attachment/mathematics/mathematics-09-01180/article_deploy/mathematics-09-01180.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b5/7c/b57cf7d242fe32ddc2469f244b67e545f07b3187.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/math9111180"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Toward Scalable Neural Dialogue State Tracking Model [article]

Elnaz Nouri, Ehsan Hosseini-Asl
<span title="2018-12-03">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper proposes a new scalable and accurate neural dialogue state tracking model, based on the recently proposed Global-Local Self-Attention encoder (GLAD) model by Zhong et al. which uses global modules  ...  to share parameters between estimators for different types (called slots) of dialogue states, and uses local modules to learn slot-specific features.  ...  Conclusion In this paper, we proposed a neural model for dialogue state traking.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.00899v1">arXiv:1812.00899v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2fc75rkihzejpjpjnnsy5xnckq">fatcat:2fc75rkihzejpjpjnnsy5xnckq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200927164229/https://arxiv.org/pdf/1812.00899v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/39/25/392522dc93e8aa5d8dcea7aab9e3bc5b3c83db44.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.00899v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Transformers for One-Shot Visual Imitation [article]

Sudeep Dasari, Abhinav Gupta
<span title="2020-11-11">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
These assumptions are baked into the neural network using the Transformers attention mechanism and a self-supervised inverse dynamics loss.  ...  A neural network is trained to mimic ground truth robot actions given context video from another agent, and must generalize to unseen task instances when prompted with new videos during test time.  ...  [12] , which we augment with multi-headed self-attention [11] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.05970v1">arXiv:2011.05970v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mtnbrsyhknd6hnu66bvzbk6keu">fatcat:mtnbrsyhknd6hnu66bvzbk6keu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201113041738/https://arxiv.org/pdf/2011.05970v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/8d/0e/8d0eeb8aee3ce93c9c04f0662ee058e8eefee6bf.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.05970v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

USAAR-DFKI – The Transference Architecture for English–German Automatic Post-Editing

Santanu Pal, Hongfei Xu, Nico Herbig, Antonio Krüger, Josef van Genabith
<span title="">2019</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ofil6chs6zhkndqe6tcritiiwm" style="color: black;">Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)</a> </i> &nbsp;
Our transference model is based on a multi-encoder transformer architecture.  ...  Unlike previous approaches, it (i) uses a transformer encoder block for src, (ii) followed by a transformer decoder block, but without masking, for self-attention on mt, which effectively acts as second  ...  The responsibility for this publication  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w19-5414">doi:10.18653/v1/w19-5414</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/wmt/PalXHKG19.html">dblp:conf/wmt/PalXHKG19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dfr3px5sgvh4tizrkyrwpxzcsm">fatcat:dfr3px5sgvh4tizrkyrwpxzcsm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200505212121/https://www.aclweb.org/anthology/W19-5414.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/95/e7/95e79dbdd63e33c03fab4022d6cd6d92aad8c91d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w19-5414"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Marian: Fast Neural Machine Translation in C++

Marcin Junczys-Dowmunt, Roman Grundkiewicz, Tomasz Dwojak, Hieu Hoang, Kenneth Heafield, Tom Neckermann, Frank Seide, Ulrich Germann, Alham Fikri Aji, Nikolay Bogoychev, André F. T. Martins, Alexandra Birch
<span title="">2018</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5n6volmnonf5tn6xputi5f2t3e" style="color: black;">Proceedings of ACL 2018, System Demonstrations</a> </i> &nbsp;
We present Marian, an efficient and selfcontained Neural Machine Translation framework with an integrated automatic differentiation engine based on dynamic computation graphs.  ...  We describe the design of the encoder-decoder framework and demonstrate that a research-friendly toolkit can achieve high training and translation speed.  ...  Government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright annotation therein.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/p18-4020">doi:10.18653/v1/p18-4020</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/acl/Junczys-Dowmunt18.html">dblp:conf/acl/Junczys-Dowmunt18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vl5hb5oitrcb5nv25w54qaqnqm">fatcat:vl5hb5oitrcb5nv25w54qaqnqm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200305190302/https://www.research.ed.ac.uk/portal/files/61352907/marian_fast_neural.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f0/67/f0672d940d5aa5203045fa3ad8ef3a4e5dcd232f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/p18-4020"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Marian: Fast Neural Machine Translation in C++

Marcin Junczys-Dowmunt, Roman Grundkiewicz, Tomasz Dwojak, Hieu Hoang, Kenneth Heafield, Tom Neckermann, Frank Seide, Ulrich Germann, Alham Fikri Aji, Nikolay Bogoychev, Andre F. T. Martins, Alexandra Birch
<span title="2018-07-15">2018</span> <i title="Zenodo"> Zenodo </i> &nbsp;
We present Marian, an efficient and selfcontained Neural Machine Translation framework with an integrated automatic differentiation engine based on dynamic computation graphs.  ...  We describe the design of the encoder-decoder framework and demonstrate that a research-friendly toolkit can achieve high training and translation speed.  ...  Government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright annotation therein.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.2551642">doi:10.5281/zenodo.2551642</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/52weuuur5fb73nvcybgog6a7ei">fatcat:52weuuur5fb73nvcybgog6a7ei</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200217232003/https://zenodo.org/record/2551642/files/P18-4020.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e5/34/e534935710a038d92c94d12efee0465cec299a35.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.2551642"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> zenodo.org </button> </a>

Attention Mechanism in Neural Networks: Where it Comes and Where it Goes [article]

Derya Soydaner
<span title="2022-04-27">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The goal of this paper is to provide an overview from the early work on searching for ways to implement attention idea with neural networks until the recent trends.  ...  A long time ago in the machine learning literature, the idea of incorporating a mechanism inspired by the human visual system into neural networks was introduced.  ...  For instance, a deep learning model learned a number of large-scale tasks from multiple domains with the aid of self-attention mechanism [86] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.13154v1">arXiv:2204.13154v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lziyvfr5gfgp5limgpm4cizgxq">fatcat:lziyvfr5gfgp5limgpm4cizgxq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220430015608/https://arxiv.org/pdf/2204.13154v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4a/c4/4ac43d51e77da91541c1f79fe3d04ac914645f57.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.13154v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

ProcessTransformer: Predictive Business Process Monitoring with Transformer Network [article]

Zaharah A. Bukhsh, Aaqib Saeed, Remco M. Dijkman
<span title="2021-04-01">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose ProcessTransformer, an approach for learning high-level representations from event logs with an attention-based network.  ...  Nevertheless, designing a deep neural architecture that performs competitively across various tasks is challenging as existing methods fail to capture long-range dependencies in the input sequences and  ...  Fig. 3 . 3 Illustration of self-attention mechanism on a trace. The model learns attention scores of events for solving a particular predictive monitoring task.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.00721v1">arXiv:2104.00721v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jlxhtdp5cnfd5dfdywc6butp6i">fatcat:jlxhtdp5cnfd5dfdywc6butp6i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210406001234/https://arxiv.org/pdf/2104.00721v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/06/fd/06fd337667d8fd38f6685e146adddc03fc8ce6dc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.00721v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Exploiting Method Names to Improve Code Summarization: A Deliberation Multi-Task Learning Approach [article]

Rui Xie, Wei Ye, Jinan Sun, Shikun Zhang
<span title="2021-03-30">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we design a novel multi-task learning (MTL) approach for code summarization through mining the relationship between method code summaries and method names.  ...  The experiment results show that our technique can be easily applied to many state-of-the-art neural models for code summarization and improve their performance.  ...  Our main contributions are: • We proposed a Deliberation Multi-task learning Approach for COde Summarization (DMACOS).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.11448v2">arXiv:2103.11448v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uwifawy34nbobpysnhzorlbnhq">fatcat:uwifawy34nbobpysnhzorlbnhq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210401001418/https://arxiv.org/pdf/2103.11448v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/db/06/db0698abb06369d8e1ea5c048d6eeb0798c52c75.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.11448v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Unified Review of Deep Learning for Automated Medical Coding [article]

Shaoxiong Ji and Wei Sun and Hang Dong and Honghan Wu and Pekka Marttinen
<span title="2022-01-08">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, it lacks a unified view of the design of neural network architectures for medical coding.  ...  Recent advances in deep learning models in natural language processing have been widely applied to this task.  ...  techniques and develop complex neural network architectures to learn rich text features for automatic medical code assignment.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.02797v1">arXiv:2201.02797v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ajl6uq6mkzdo3j2trmfy5ceypq">fatcat:ajl6uq6mkzdo3j2trmfy5ceypq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220112030202/https://arxiv.org/pdf/2201.02797v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a1/1e/a11e5bd5918c7580573738b92657af99494fbb51.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.02797v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Improved Transformer for High-Resolution GANs [article]

Long Zhao, Zizhao Zhang, Ting Chen, Dimitris N. Metaxas, Han Zhang
<span title="2021-12-24">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Second, in high-resolution stages, we drop self-attention while only keeping multi-layer perceptrons reminiscent of the implicit neural function.  ...  First, in low-resolution stages of the generative process, standard global self-attention is replaced with the proposed multi-axis blocked self-attention which allows efficient mixing of local and global  ...  Acknowledgements We thank Chitwan Saharia, Jing Yu Koh, and Kevin Murphy for their feedback to the paper.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.07631v3">arXiv:2106.07631v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7hqlal6uczapxjyg2bcvzslfcq">fatcat:7hqlal6uczapxjyg2bcvzslfcq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211120190234/https://arxiv.org/pdf/2106.07631v2.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/8c/59/8c597d0a28dceeda7ed9d73c532a0cfdcbc8fe1f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.07631v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Self-Attention: A Better Building Block for Sentiment Analysis Neural Network Classifiers

Artaches Ambartsoumian, Fred Popowich
<span title="">2018</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5w4agftuibe35hbonabjurfqf4" style="color: black;">Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis</a> </i> &nbsp;
Recently, a new category of neural networks, self-attention networks (SANs), have been created which utilizes the attention mechanism as the basic building block.  ...  Self-attention networks have been shown to be effective for sequence modeling tasks, while having no recurrence or convolutions.  ...  Acknowledgments We thank the anonymous reviewers for their insightful suggestions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w18-6219">doi:10.18653/v1/w18-6219</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/wassa/AmbartsoumianP18.html">dblp:conf/wassa/AmbartsoumianP18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/u74iyv56cnftlpxeaz22bud4wa">fatcat:u74iyv56cnftlpxeaz22bud4wa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200507194158/https://www.aclweb.org/anthology/W18-6219.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/78/12/7812f610375811a3305ae44913aa184f68bfa5fb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w18-6219"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 20,800 results